Monitor GPU Usage With nvtop Instead of nvidia-smi
Melvin Vivas · X post · 2026-07-18 · Open on X
Topics: LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity · Level: beginner
Summary
The creator recommends nvtop, an interactive, htop-style GPU monitor, instead of running nvidia-smi to check GPU usage. It's a handy tool for anyone running local models.
Key points
- nvidia-smi gives a one-off snapshot of GPU usage
- nvtop is an interactive, htop-style monitor showing GPU use, memory and processes over time
- Useful when running local model inference or training
Resources mentioned
- nvtop · tool · github.com · free
An open-source, top-style monitor for GPU usage in the terminal.
Also in: GPU devbox Docker image with coding agents on Runpod (Melvin Vivas on X · notes), GPU-Ready AI Devbox Docker Image on Runpod (PyTorch 2.8 + CUDA 12.8) (Melvin Vivas on X · notes) - nvidia-smi · tool · developer.nvidia.com · free
An NVIDIA command-line tool that shows the attached GPU, its VRAM and how much is in use.
Also in: Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes)
Try this
- Install nvtop to monitor GPU usage while running local models
More in LLMOps, Deployment & Monitoring
- Personal AI Computer to Run DeepSeek V4-Flash Locally
- Running DeepSeek V4 Flash Locally: RAM Needs for 4-bit and 3-bit Quants
- aibackends 0.3.0: Model Caching Speeds Up PII and OCR Inference
- Cost-Saving Model Fallback Chain: Grok → Codex → OpenRouter DeepSeek
- Running a Personal AI Agent for $0.69/Day with DeepSeek V4 Flash
- Hosting a Personal AI Agent: Local Mac Mini vs Cloud VM Privacy Trade-off